The popular social photo sharing site is adding the ability for people to take a photo of things in the real-world and get recommendations for similar products on Pinterest. For example, If you take a photo of a room with a purse and a lamp on a table that you like, Pinterest will show you results for all three items.
Using TITAN X GPUs and the Caffe deep learning framework, the team trained their convolutional neural networks on millions of images uploaded by Pinterest users and then used GPUs in the Amazon cloud to both detect and classify objects in real-time.
TechCrunch mentions that the new visual search capability could help Pinterest evolve into an online shopping experience with the ability to tap into users at all moments in the purchasing process, from becoming aware of certain products and brands, to searching for them and declaring interest, and then actually buying them.
The visual search functionality will roll out to Pinterest users in the next few weeks.
Read more >>
Pinterest Introduces the Future of Visual Search
Jun 30, 2016
Discuss (0)
Related resources
- GTC session: Evolution of Recommender Model Serving from CPUs to GPUs
- GTC session: Revolutionizing Vision AI: From 2D to 3D Worlds
- GTC session: Tencent Text-to-Image Generative Model
- NGC Containers: Eye Contact
- SDK: Falcor
- SDK: NVIDIA Texture Tools-Photoshop Plug in
About the Authors
